import urllib.request
url = 'https://dianying.taobao.com/showAction.json?_ksTS=1706607773138_64&jsoncallback=jsonp65&action=showAction&n_s=new&event_submit_doGetSoon=true'
headers = {
'Accept':'text/javascript, application/javascript, application/ecmascript, application/x-ecmascript, */*; q=0.01',
#'Accept-Encoding':'gzip, deflate, br',
'Accept-Language':'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
'Bx-V':'2.5.10',
'Cookie':'t=1711f0888e4c2a7e91b85fe007a61511; cookie2=1939a42c5bfbadf3a50d13aaf53a3948; v=0; _tb_token_=e7b61e81f3e53; cna=hrI/HudTx0sCAW8xRmtQHefK; xlly_s=1; tb_city=610100; tb_cityName="zvewsg=="; isg=BDIybH3bg_VcrL_J6P1WPg64g3gUwzZdz7m8k_wJ3OXQj9CJ5FCmbUyufysz_671; tfstk=eS2w3mx-LOBNka-7_XDqThBlAEMthYQ53-gjmoqmfV0Gk5M4glaZGPZmlxz4urusiNH_3ykTd59j5NH4mzMVPa65FlEtBxb5PM0tiZMAb2NpWTZTXHc1GO5dFK-ke6SKQ7K1rBlCru03LbXEx9Gaj2JzvJoisCEi8KJ4LWlZrLgenK2EbgSXkD0pK-FwoIlivDu5YMkgg9gEY31HGIdx6WnEPGI9MIhivDu5YMRvMfH-Y4sOX',
'Referer':'https://dianying.taobao.com/?spm=a1z21.3046609.city.11.32c0112a7jFe7B&city=610100',
'Sec-Ch-Ua':'"Not_A Brand";v="8", "Chromium";v="120", "Microsoft Edge";v="120"',
'Sec-Ch-Ua-Mobile':'?0',
'Sec-Ch-Ua-Platform':'"Windows"',
'Sec-Fetch-Dest':'empty',
'Sec-Fetch-Mode':'cors',
'Sec-Fetch-Site':'same-origin',
'X-Requested-With':'XMLHttpRequest',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0',
}
request = urllib.request.Request(url = url,headers = headers)
response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')
content = content.split('(')[1].split(')')[0]
with open('taopiaopiao.json','w',encoding = 'utf-8') as fp:
fp.write(content)
import json
import jsonpath
obj = json.load(open('taopiaopiao.json',encoding='utf-8'))
director_list = jsonpath.jsonpath(obj,'$..director')
print(director_list)
需要注意的事项:
1、注意headers中哪些请求头信息不能丢。
2、如果使用json.load出现报错,那么需要注意encoding的设置。
3、获取的content需要进行切片操作才能成为标准的json文件。